© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9363
    Prev
    Next
    INDEX
    Explanations

    Houdini simulation, resolution, domain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    o
    0.49
     tasso
    0.45
     зарубе
    0.38
    t
    0.38
    marketplace
    0.37
    sized
    0.37
    рев
    0.37
    ogg
    0.37
    ীক
    0.36
    Threshold
    0.36
    POSITIVE LOGITS
    ]
    0.42
     বলে
    0.42
     scheint
    0.42
     цього
    0.42
     डिज़ाइन
    0.41
     pozwala
    0.41
    コンパクト
    0.40
    ADEM
    0.40
    ènes
    0.39
     blijkt
    0.39
    Activations Density 0.025%

    No Known Activations